This paper describes how advanced deeplearning based computer vision algorithms are applied to enable real-time on-board sensor processing for small UAVs. Four use cases are considered: target detection, classificati...
详细信息
Agricultural robots are rapidly becoming more advanced with the development of relevant technologies and in great demand to guarantee food supply. As such, they are slated to play an important role in precision agricu...
详细信息
Agricultural robots are rapidly becoming more advanced with the development of relevant technologies and in great demand to guarantee food supply. As such, they are slated to play an important role in precision agriculture. For tomato production, harvesting employs over 40% of the total workforce. Therefore, it is meaningful to develop a robot harvester to assist workers. The objective of this work is to understand the factors restricting the recognition accuracy using imageprocessing and deeplearning methods, and improve the performance of crop detection in agricultural complex environment. With the accurate recognition of the growing status and location of crops, temporal management of the crop and selective harvesting can be available, and issues caused by the growing shortage of agricultural labour can be alleviated. In this respect, this work integrates the classic imageprocessing methods with the YOLOv5 (You only look once version 5) network to increase the accuracy and robustness of tomato and stem perception. As a consequence, an algorithm to estimate the degree of maturity of truss tomatoes (clusters of individual tomatoes) and an integrated method to locate stems based on the resultant experiments error of each individual method were proposed. Both indoor and real-filed tests were carried out using a robot harvester. The results proved the high accuracy of the proposed algorithms under varied illumination conditions, with an average deviation of 2 mm from the ground-truth. The robot can be guided to harvest truss tomatoes efficiently, with an average operating time of 9 s/cluster.
The ability to detect anomalies in time series is considered highly valuable in numerous application domains. The sequential nature of time series objects is responsible for an additional feature complexity, ultimatel...
详细信息
The ability to detect anomalies in time series is considered highly valuable in numerous application domains. The sequential nature of time series objects is responsible for an additional feature complexity, ultimately requiring specialized approaches in order to solve the task. Essential characteristics of time series, situated outside the time domain, are often difficult to capture with state-of-the-art anomaly detection methods when no transformations have been applied to the time series. Inspired by the success of deeplearning methods in computer vision, several studies have proposed transforming time series into image-like representations, used as inputs for deeplearning models, and have led to very promising results in classification tasks. In this paper, we first review the signal to image encoding approaches found in the literature. Second, we propose modifications to some of their original formulations to make them more robust to the variability in large datasets. Third, we compare them on the basis of a common unsupervised task to demonstrate how the choice of the encoding can impact the results when used in the same deeplearning architecture. We thus provide a comparison between six encoding algorithms with and without the proposed modifications. The selected encoding methods are Gramian Angular Field, Markov Transition Field, recurrence plot, grey scale encoding, spectrogram, and scalogram. We also compare the results achieved with the raw signal used as input for another deeplearning model. We demonstrate that some encodings have a competitive advantage and might be worth considering within a deeplearning framework. The comparison is performed on a dataset collected and released by Airbus SAS, containing highly complex vibration measurements from real helicopter flight tests. The different encodings provide competitive results for anomaly detection.
Palm recognition systems play an important role in biometric authentication;however, existing systems frequently have low accuracy and resiliency due to problems such as changing lighting conditions, occlusions, and h...
详细信息
This paper presents an exploration of object detection, a critical application in deeplearning characterized by its robust feature learning and representation capabilities. It focuses on typical methodologies such as...
详细信息
The rapid evolution of modern medical technology has propelled surgical robots to the forefront of surgical innovation. These robots offer unprecedented accuracy and safety in procedures, empowering surgeons with adva...
详细信息
Before export, fruit should be classified to improve quality, meet customer requirements and increase product value. This article proposes a method to identify defects on the surface of tomato skin using image process...
详细信息
Multi-classification of pulmonary diseases poses a significant challenge, particularly when diseases share similar radiological presentations like lung cancer, pneumonia, and COVID-19. While chest CT scan images are e...
详细信息
The current field shows a trend of multi-dimensional fusion [1], the use of lightweight convolutional self-encoder and generative adversarial network in denoising, super-resolution tasks beyond the traditional methods...
The current field shows a trend of multi-dimensional fusion [1], the use of lightweight convolutional self-encoder and generative adversarial network in denoising, super-resolution tasks beyond the traditional methods, and multimodal fusion technology through the integration of visible/infrared/depth map data to enhance feature extraction. In future, it is necessary to build a quantum entanglement parallel denoising system, develop neural radiation field three-dimensional dynamic reconstruction technology, and integrate optoelectronic hardware design to guarantee data security [2].A self-supervised and comparative learning framework significantly reduces the dependence on labeled data [3], and the attention mechanism is combined with reinforcement learning to optimize dynamic sampling. In future, it is necessary to build a self-supervised contrast collaboration framework, develop Transformer–dynamic convolution hybrid architecture [4], and strengthen cross-scale modeling and *** Transformer dominates image classification and segmentation through the self-attention mechanism, and dynamic sparse attention improves real-time analysis capabilities [5]. In future, we need to design a multimodal synergy framework, develop a physical embedding model to integrate a priori knowledge such as light field equations, and combine it with dynamic pruning to balance performance [6].In the field of intelligent transportation, multi-sensor fusion is used to build high-precision 3D environment models [7], event cameras help to break through the traditional frame rate limitations, and federated learning is employed to optimize global traffic prediction. In future, we need to develop an impulse neural network to drive heterogeneous data alignment, construct a meta-learning cross-domain adaptive framework, and establish a privacy security sharing mechanism [8].End-to-end models are employed to realize the accurate classification of agricultural pests and diseases, whe
This paper proposes an approach to convert real life images into cartoon images using imageprocessing. The cartoon images have sharp edges, reduced colour quantity compared to the original image, and smooth colour re...
详细信息
暂无评论